计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (9): 160-167.doi: 10.11896/jsjkx.220700035

• 数据库&大数据&数据科学 • 上一篇    下一篇

面向移动应用评分推荐的多任务图嵌入深度预测模型

李海明1, 朱智蘅1, 刘磊2, 过辰楷3   

  1. 1 上海电力大学计算机科学与技术学院 上海 201306
    2 南开大学人工智能学院 天津 300350
    3 南开大学网络空间安全学院 天津 300350
  • 收稿日期:2022-07-04 修回日期:2022-10-12 出版日期:2023-09-15 发布日期:2023-09-01
  • 通讯作者: 过辰楷(guochenkai@nankai.edu.cn)
  • 作者简介:(shdianli2022@163.com)
  • 基金资助:
    国家自然科学基金(62002177);天津市科技计划项目(20YDTPJC01810);南开大学2022年实验课程改革项目(22NKSYSX05);教育部-华为产学合作协同育人项目(202002142035)

Multi-task Graph-embedding Deep Prediction Model for Mobile App Rating Recommendation

LI Haiming1, ZHU Zhiheng1, LIU Lei2, GUO Chenkai3   

  1. 1 College of Computer Science and Technology,Shanghai University of Electric Power,Shanghai 201306,China
    2 College of Artificial Intelligence,Nankai University,Tianjin 300350,China
    3 College of Cyber Science,Nankai University,Tianjin 300350,China
  • Received:2022-07-04 Revised:2022-10-12 Online:2023-09-15 Published:2023-09-01
  • About author:LI Haiming,born in 1964,Ph.D,professor,master supervisor.His main research interests include intelligent information processing and power informatization.
    GUO Chenkai,born in 1988,Ph.D,associate professor,master supervisor,is a member of China Computer Federation.His main research interests include intelligent software engineering and code analysis of mobile app.
  • Supported by:
    National Natural Science Foundation of China(62002177),Science and Technology Planning Project of Tianjin City(20YDTPJC01810),2022 Experimental Course Reform Project of Nankai University(22NKSYSX05) and Ministry of Education Industry University Cooperation Collaborative Education Project(202002142035).

PDF (PC)

1029

摘要： 随着智能终端设备以及移动应用软件的普及,用户对应用质量的要求和用户体验需要愈发凸显。移动应用的评分推荐作为一项有效的事前评估手段,逐渐得到市场关注。传统的应用评分推荐工作主要围绕解决数据稀疏和模型深度问题,未能对应用推荐本身的图结构、多任务形态进行准确表征。针对该问题,提出了一种面向移动应用评分推荐的图嵌入多任务模型AppGRec,利用归纳型二部图的嵌入结构对特征中的用户交互关系进行挖掘,并使用shared-bottom多任务模型捕获应用评分中的多任务特点,同时兼顾了数据稀疏和模型深度的影响。在Google Play上收集了16 031个有效的移动应用及其特征数据作为验证数据集,实验结果表明,AppGRec在MAE和RMSE上相比state-of-the-art模型分别提升了10.4%和10.9%。此外,对AppGRec超参和核心模块的影响做了具体分析,多角度验证其有效性。

关键词: 移动应用, 推荐系统, 图嵌入, 深度学习, 神经网络, 评分预测

Abstract: With the prevalence of smart terminal devices and mobile application(app for short),the requirements for application quality and user experience gradually increase.As an effective pre-assessment method,mobile app rating recommendation has gained increasing attention from app markets.The traditional app rating and recommendation works mainly focus on challenges such as data sparsity and model depth.Nevertheless,they fail to accurately capture the graph relationship within the apps and users.Furthermore,the multi-task characteristic of app recommendation is neglected.Aiming at these shortcomings,this paper proposes a graph embedding multi-task model AppGRec for mobile app rating and recommendation.AppGRec uses the embedding structure of inductive bipartite graph to mine the user interaction features.It uses the shared-bottom based model to capture the multi-task feature in app rating,while considering the effects of data sparsity and model depth.16 031 valid mobile apps and their feature data on Google Play are collected as dataset for method evaluation.Experimental results show that AppGRec achieves 10.4% and 10.9% improvement in terms of MAE and RMSE respectively comparing with the state-of-the-art models.In addition,this paper also makes quantitative analysis of the impact of hyperparameters and some core modules in AppGRec,and verifies the effectiveness from multiple perspectives.

Key words: Mobile app, Recommendation system, Graph embedding, Deep learning, Neural network, Rating prediction

中图分类号: 

  • TP391
[1]KOREN Y.Collaborative filtering with temporal dynamics[C]//Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and data Mining.2009:447-456.
[2]GUO H,TANG R,YE Y,et al.DeepFM:a factorization-ma-chine based neural network for CTR prediction[J].arXiv:1703.04247,2017.
[3]KOREN Y,BELL R,VOLINSKY C.Matrix factorization techniques for recommender systems[J].Computer,2009,42(8):30-37.
[4]ELKAHKY A M,SONG Y,HE X.A multi-view deep learning approach for cross domain user modeling in recommendation systems[C]//Proceedings of the 24th International Conference on World Wide Web.2015:278-288.
[5]WANG H,ZHANG F,XIE X,et al.DKN:Deep knowledge-aware networkfor news recommendation[C]//Proceedings of the 2018 World Wide Web Conference.2018:1835-1844.
[6]HE X,LIAO L,ZHANG H,et al.Neural collaborative filtering[C]//Proceedings of the 26th International conference on World Wide Web.2017:173-182.
[7]WANG X,HE X,CAO Y,et al.Kgat:Knowledge graph atten-tion network for recommendation[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Disco-very & Data Mining.2019:950-958.
[8]FOUSS F,PIROTTE A,RENDERS J M,et al.Random-walkcomputation of similarities between nodes of a graph with application to collaborative recommendation[J].IEEE Transactions on Knowledge and Data Engineering,2007,19(3):355-369.
[9]FAN W,MA Y,LI Q,et al.Graph neural networks for social recommendation[C]//The World Wide Web Conference.2019:417-426.
[10]BAE D,HAN K,PARK J,et al.AppTrends:A graph-based mobile app recommendation system using usage history[C]//2015 International Conference on Big Data and Smart Computing(BIGCOMP).IEEE,2015:210-216.
[11]OUYANG Y,GUO B,TANG X,et al.Mobile App Cross-Domain Recommendation with Multi-Graph Neural Network[J].ACM Transactions on Knowledge Discovery from Data(TKDD),2021,15(4):1-21.
[12]YU H,XIA X,ZHAO X,et al.Combining collaborative filtering and topic modeling for more accurate android mobile app library recommendation[C]//Proceedings of the 9th Asia-Pacific Symposium on Internetware.2017:1-6.
[13]LIN K P,CHANG Y W,SHEN C Y,et al.Leveraging onlineword of mouth for personalized app recommendation[J].IEEE Transactions on Computational Social Systems,2018,5(4):1061-1070.
[14]YIN H,CHEN L,WANG W,et al.Mobi-sage:A sparse additive generative model for mobile app recommendation[C]//2017 IEEE 33rd International Conference on Data Engineering(ICDE).IEEE,2017:75-78.
[15]CAO D,NIE L,HE X,et al.Version-sensitive mobile app re-commendation[J].Information Sciences,2017,381:161-175.
[16]YAO Y,ZHAO W X,WANG Y,et al.Version-aware ratingprediction for mobile app recommendation[J].ACM Transactions on Information Systems(TOIS),2017,35(4):1-33.
[17]LIU B,WU Y,GONG N Z,et al.Structural analysis of user choices for mobile app recommendation[J].ACM Transactions on Knowledge Discovery from Data(TKDD),2016,11(2):1-23.
[18]TU Z,LI Y,HUI P,et al.Personalized Mobile App Recommendation by Learning User's Interest from Social Media[J].IEEE Transactions on Mobile Computing,2019,19(11):2670-2683.
[19]XU Y,ZHU Y,SHEN Y,et al.Leveraging app usage contexts for app recommendation:a neural approach[J].World Wide Web,2019,22(6):2721-2745.
[20]LIANG T,SHENG X,ZHOU L,et al.Mobile app recommendation via heterogeneous graph neural network in edge computing[J].Applied Soft Computing,2021,103:107162.
[21]XIE F,CAO Z,XU Y,et al.Graph neural network and multi-view learning based mobile application recommendation in hete-rogeneous graphs[C]//2020 IEEE International Conference on Services Computing(SCC).IEEE,2020:100-107.
[22]ZHANG M,ZHAO J,DONG H,et al.A knowledge graph based approach for mobile application recommendation[C]//International Conference on Service-Oriented Computing.Cham:Springer,2020:355-369.
[23]GUO C,XU Y,HOU X,et al.Deep attentive factorization machine for app recommendation service[C]//2019 IEEE International Conference on Web Services(ICWS).IEEE,2019:134-138.
[24]MIKOLOV T,SUTSKEVER I,CHEN K,et al.Distributed representations of words and phrases and their compositionality[J].arXiv:1310.4546,2013.
[25]YING R,HE R,CHEN K,et al.Graph convolutional neural net-works for web-scale recommender systems[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.2018:974-983.
[26]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016.
[27]VELIC＇KOVICˇ P,CUCURULL G,CASANOVA A,et al.Graph attention networks[J].arXiv:1710.10903,2017.
[28]HAMILTON W,YING Z T,LESKOVEC J.Inductive representation learning on large graphs[C]//Proceedings of Advances in Neural Information Processing Systems.2017:1024-1034.
[29]SALAKHUTDINOV R,MNIH A.Probabilistic matrix factorization[C]//Proceedings of Advances in Neural Information Processing Systems.2007:1257-1264.
[30]RENDLE S.Factorization machines[C]//2010 IEEE International Conference on Data Mining.IEEE,2010:995-1000.
[31]SHAZEER N,MIRHOSEINI A,MAZIARZ K,et al.Outra-geously large neural networks:The sparsely-gated mixture-of-experts layer[J].arXiv:1701.06538,2017.
[32]MA J,ZHAO Z,YI X,et al.Modeling task relationships inmulti-task learning with multi-gate mixture-of-experts[C]//Proceedings of the 24th ACM SIGKDD InternationalConfe-rence on Knowledge Discovery & Data Mining.2018:1930-1939.
[33]CHEN C,ZHANG M,LIU Y,et al.Neural attentional rating regression with review-level explanations[C]//Proceedings of the 2018 World Wide Web Conference.2018:1583-1592.
[34]WANG X,HE X,WANG M,et al.Neural graph collaborativefiltering[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval.2019:165-174.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发